import numpy as np
import pandas as pd
import os
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px

os.chdir('C:\\Users\\lance\OneDrive\Desktop\\Feynn Labs\\')

df=pd.read_csv('Placement_Data_Full_Class.csv')

df

	sl_no	gender	ssc_p	ssc_b	hsc_p	hsc_b	hsc_s	degree_p	degree_t	workex	etest_p	specialisation	mba_p	status	salary
0	1	M	67.00	Others	91.00	Others	Commerce	58.00	Sci&Tech	No	55.0	Mkt&HR	58.80	Placed	270000.0
1	2	M	79.33	Central	78.33	Others	Science	77.48	Sci&Tech	Yes	86.5	Mkt&Fin	66.28	Placed	200000.0
2	3	M	65.00	Central	68.00	Central	Arts	64.00	Comm&Mgmt	No	75.0	Mkt&Fin	57.80	Placed	250000.0
3	4	M	56.00	Central	52.00	Central	Science	52.00	Sci&Tech	No	66.0	Mkt&HR	59.43	Not Placed	NaN
4	5	M	85.80	Central	73.60	Central	Commerce	73.30	Comm&Mgmt	No	96.8	Mkt&Fin	55.50	Placed	425000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
210	211	M	80.60	Others	82.00	Others	Commerce	77.60	Comm&Mgmt	No	91.0	Mkt&Fin	74.49	Placed	400000.0
211	212	M	58.00	Others	60.00	Others	Science	72.00	Sci&Tech	No	74.0	Mkt&Fin	53.62	Placed	275000.0
212	213	M	67.00	Others	67.00	Others	Commerce	73.00	Comm&Mgmt	Yes	59.0	Mkt&Fin	69.72	Placed	295000.0
213	214	F	74.00	Others	66.00	Others	Commerce	58.00	Comm&Mgmt	No	70.0	Mkt&HR	60.23	Placed	204000.0
214	215	M	62.00	Central	58.00	Others	Science	53.00	Comm&Mgmt	No	89.0	Mkt&HR	60.22	Not Placed	NaN

215 rows × 15 columns

df.describe()

	sl_no	ssc_p	hsc_p	degree_p	etest_p	mba_p	salary
count	215.000000	215.000000	215.000000	215.000000	215.000000	215.000000	148.000000
mean	108.000000	67.303395	66.333163	66.370186	72.100558	62.278186	288655.405405
std	62.209324	10.827205	10.897509	7.358743	13.275956	5.833385	93457.452420
min	1.000000	40.890000	37.000000	50.000000	50.000000	51.210000	200000.000000
25%	54.500000	60.600000	60.900000	61.000000	60.000000	57.945000	240000.000000
50%	108.000000	67.000000	65.000000	66.000000	71.000000	62.000000	265000.000000
75%	161.500000	75.700000	73.000000	72.000000	83.500000	66.255000	300000.000000
max	215.000000	89.400000	97.700000	91.000000	98.000000	77.890000	940000.000000

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 215 entries, 0 to 214
Data columns (total 15 columns):
 #   Column          Non-Null Count  Dtype  
---  ------          --------------  -----  
 0   sl_no           215 non-null    int64  
 1   gender          215 non-null    object 
 2   ssc_p           215 non-null    float64
 3   ssc_b           215 non-null    object 
 4   hsc_p           215 non-null    float64
 5   hsc_b           215 non-null    object 
 6   hsc_s           215 non-null    object 
 7   degree_p        215 non-null    float64
 8   degree_t        215 non-null    object 
 9   workex          215 non-null    object 
 10  etest_p         215 non-null    float64
 11  specialisation  215 non-null    object 
 12  mba_p           215 non-null    float64
 13  status          215 non-null    object 
 14  salary          148 non-null    float64
dtypes: float64(6), int64(1), object(8)
memory usage: 25.3+ KB

plt.figure()
df['salary'].plot(kind='density')
skew_sal=df['salary'].skew()
kurt_sal=df['salary'].kurt()
print('skew_sal:{}'.format(skew_sal))
print('kurt_sal:{}'.format(kurt_sal))

skew_sal:3.5697471998711054
kurt_sal:18.54427337222016

plt.figure()
df['mba_p'].plot(kind='density')
skew_mba_p=df['mba_p'].skew()
kurt_mba_p=df['mba_p'].kurt()
print('skew_mba_p:{}'.format(skew_mba_p))
print('kurt_mba_p:{}'.format(kurt_mba_p))

skew_mba_p:0.31357565317840763
kurt_mba_p:-0.47072269614559437

px.histogram(df,x='salary',color='specialisation')

px.histogram(df,x='salary',histnorm='probability density')

px.histogram(df,x='salary',color='gender')

px.histogram(df,x='status',color='specialisation')

import  scipy.stats  as stats

df_table=pd.crosstab(df['specialisation'],df['status'])

print(df_table)

status          Not Placed  Placed
specialisation                    
Mkt&Fin                 25      95
Mkt&HR                  42      53

Observed_Values=df_table.values

val=stats.chi2_contingency(df_table)
val

(12.440229009203623,
 0.00042018425858864284,
 1,
 array([[37.39534884, 82.60465116],
        [29.60465116, 65.39534884]]))

Expected_Values=val[3]
Expected_Values

array([[37.39534884, 82.60465116],
       [29.60465116, 65.39534884]])

no_of_rows=len(df_table.iloc[0:2,0])
no_of_columns=len(df_table.iloc[0,0:2])
ddof=(no_of_rows-1)*(no_of_columns-1)
print("Degree of Freedom:-",ddof)
alpha = 0.05

Degree of Freedom:- 1

from scipy.stats import chi2
chi_square=sum([(o-e)**2./e for o,e in zip(Observed_Values,Expected_Values)])
chi_square_statistic=chi_square[0]+chi_square[1]

critical_value=chi2.ppf(q=1-alpha,df=ddof)
print('critical_value:',critical_value)

critical_value: 3.841458820694124

#p-value
p_value=1-chi2.cdf(x=chi_square_statistic,df=ddof)
print('p-value:',p_value)
print('Significance level: ',alpha)
print('Degree of Freedom: ',ddof)
print('p-value:',p_value)

p-value: 0.0002375467465819403
Significance level:  0.05
Degree of Freedom:  1
p-value: 0.0002375467465819403

if chi_square_statistic>=critical_value:
    print("Reject H0,There is a relationship between 2 categorical variables")
else:
    print("Retain H0,There is no relationship between 2 categorical variables")
    
if p_value<=alpha:
    print("Reject H0,There is a relationship between 2 categorical variables")
else:
    print("Retain H0,There is no relationship between 2 categorical variables")

Reject H0,There is a relationship between 2 categorical variables
Reject H0,There is a relationship between 2 categorical variables

df1=df.copy()

X = df1. drop(labels='status', axis=1)

X

	sl_no	gender	ssc_p	ssc_b	hsc_p	hsc_b	hsc_s	degree_p	degree_t	workex	etest_p	specialisation	mba_p	salary
0	1	M	67.00	Others	91.00	Others	Commerce	58.00	Sci&Tech	No	55.0	Mkt&HR	58.80	270000.0
1	2	M	79.33	Central	78.33	Others	Science	77.48	Sci&Tech	Yes	86.5	Mkt&Fin	66.28	200000.0
2	3	M	65.00	Central	68.00	Central	Arts	64.00	Comm&Mgmt	No	75.0	Mkt&Fin	57.80	250000.0
3	4	M	56.00	Central	52.00	Central	Science	52.00	Sci&Tech	No	66.0	Mkt&HR	59.43	NaN
4	5	M	85.80	Central	73.60	Central	Commerce	73.30	Comm&Mgmt	No	96.8	Mkt&Fin	55.50	425000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
210	211	M	80.60	Others	82.00	Others	Commerce	77.60	Comm&Mgmt	No	91.0	Mkt&Fin	74.49	400000.0
211	212	M	58.00	Others	60.00	Others	Science	72.00	Sci&Tech	No	74.0	Mkt&Fin	53.62	275000.0
212	213	M	67.00	Others	67.00	Others	Commerce	73.00	Comm&Mgmt	Yes	59.0	Mkt&Fin	69.72	295000.0
213	214	F	74.00	Others	66.00	Others	Commerce	58.00	Comm&Mgmt	No	70.0	Mkt&HR	60.23	204000.0
214	215	M	62.00	Central	58.00	Others	Science	53.00	Comm&Mgmt	No	89.0	Mkt&HR	60.22	NaN

215 rows × 14 columns

y=df1['status']

y.shape

(215,)

sns.pairplot(df1,hue='status',height=3)

<seaborn.axisgrid.PairGrid at 0x18acf08ce80>

df1.nunique()

sl_no             215
gender              2
ssc_p             103
ssc_b               2
hsc_p              97
hsc_b               2
hsc_s               3
degree_p           89
degree_t            3
workex              2
etest_p           100
specialisation      2
mba_p             205
status              2
salary             45
dtype: int64

X.isna().sum()

sl_no              0
gender             0
ssc_p              0
ssc_b              0
hsc_p              0
hsc_b              0
hsc_s              0
degree_p           0
degree_t           0
workex             0
etest_p            0
specialisation     0
mba_p              0
salary            67
dtype: int64

y.isna().sum()

0

df.plot(kind='box')

<AxesSubplot:>

X.hist(figsize=(15,10))

array([[<AxesSubplot:title={'center':'sl_no'}>,
        <AxesSubplot:title={'center':'ssc_p'}>,
        <AxesSubplot:title={'center':'hsc_p'}>],
       [<AxesSubplot:title={'center':'degree_p'}>,
        <AxesSubplot:title={'center':'etest_p'}>,
        <AxesSubplot:title={'center':'mba_p'}>],
       [<AxesSubplot:title={'center':'salary'}>, <AxesSubplot:>,
        <AxesSubplot:>]], dtype=object)

y.hist()

<AxesSubplot:>

#fill missing Values
X['salary'].fillna(X['salary'].median(),inplace=True)

X

	sl_no	gender	ssc_p	ssc_b	hsc_p	hsc_b	hsc_s	degree_p	degree_t	workex	etest_p	specialisation	mba_p	salary
0	1	M	67.00	Others	91.00	Others	Commerce	58.00	Sci&Tech	No	55.0	Mkt&HR	58.80	270000.0
1	2	M	79.33	Central	78.33	Others	Science	77.48	Sci&Tech	Yes	86.5	Mkt&Fin	66.28	200000.0
2	3	M	65.00	Central	68.00	Central	Arts	64.00	Comm&Mgmt	No	75.0	Mkt&Fin	57.80	250000.0
3	4	M	56.00	Central	52.00	Central	Science	52.00	Sci&Tech	No	66.0	Mkt&HR	59.43	265000.0
4	5	M	85.80	Central	73.60	Central	Commerce	73.30	Comm&Mgmt	No	96.8	Mkt&Fin	55.50	425000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
210	211	M	80.60	Others	82.00	Others	Commerce	77.60	Comm&Mgmt	No	91.0	Mkt&Fin	74.49	400000.0
211	212	M	58.00	Others	60.00	Others	Science	72.00	Sci&Tech	No	74.0	Mkt&Fin	53.62	275000.0
212	213	M	67.00	Others	67.00	Others	Commerce	73.00	Comm&Mgmt	Yes	59.0	Mkt&Fin	69.72	295000.0
213	214	F	74.00	Others	66.00	Others	Commerce	58.00	Comm&Mgmt	No	70.0	Mkt&HR	60.23	204000.0
214	215	M	62.00	Central	58.00	Others	Science	53.00	Comm&Mgmt	No	89.0	Mkt&HR	60.22	265000.0

215 rows × 14 columns

# #Removing outliars 
# import scipy.stats as stats
# #find absolute value of z-score for each observation
# z = np.abs(stats.zscore(X['salary']))

# #only keep rows in dataframe with all z-scores less than absolute value of 3 
# z = np.abs(stats.zscore(X['salary']))
# print(z)
# print(np.where(z > 3))

# Encode Target Colu
from sklearn.preprocessing import LabelEncoder
# Encode for string labels
le =LabelEncoder()
y = label_encoder.fit_transform(y)

y.shape

(215,)

y

array([1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1, 1,
       1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 1,
       1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0,
       1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0,
       1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 0, 1, 1, 0,
       1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1,
       1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1,
       1, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0,
       1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1,
       0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0])

y.shape

(215,)

X.shape

(215, 14)

X

	sl_no	gender	ssc_p	ssc_b	hsc_p	hsc_b	hsc_s	degree_p	degree_t	workex	etest_p	specialisation	mba_p	salary
0	1	M	67.00	Others	91.00	Others	Commerce	58.00	Sci&Tech	No	55.0	Mkt&HR	58.80	270000.0
1	2	M	79.33	Central	78.33	Others	Science	77.48	Sci&Tech	Yes	86.5	Mkt&Fin	66.28	200000.0
2	3	M	65.00	Central	68.00	Central	Arts	64.00	Comm&Mgmt	No	75.0	Mkt&Fin	57.80	250000.0
3	4	M	56.00	Central	52.00	Central	Science	52.00	Sci&Tech	No	66.0	Mkt&HR	59.43	265000.0
4	5	M	85.80	Central	73.60	Central	Commerce	73.30	Comm&Mgmt	No	96.8	Mkt&Fin	55.50	425000.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
210	211	M	80.60	Others	82.00	Others	Commerce	77.60	Comm&Mgmt	No	91.0	Mkt&Fin	74.49	400000.0
211	212	M	58.00	Others	60.00	Others	Science	72.00	Sci&Tech	No	74.0	Mkt&Fin	53.62	275000.0
212	213	M	67.00	Others	67.00	Others	Commerce	73.00	Comm&Mgmt	Yes	59.0	Mkt&Fin	69.72	295000.0
213	214	F	74.00	Others	66.00	Others	Commerce	58.00	Comm&Mgmt	No	70.0	Mkt&HR	60.23	204000.0
214	215	M	62.00	Central	58.00	Others	Science	53.00	Comm&Mgmt	No	89.0	Mkt&HR	60.22	265000.0

215 rows × 14 columns

#Creating pipeline
#https://towardsdatascience.com/step-by-step-tutorial-of-sci-kit-learn-pipeline-62402d5629b6

X=pd.get_dummies(X,drop_first=True)
X

	sl_no	ssc_p	hsc_p	degree_p	etest_p	mba_p	salary	gender_M	ssc_b_Others	hsc_b_Others	hsc_s_Commerce	hsc_s_Science	degree_t_Others	degree_t_Sci&Tech	workex_Yes	specialisation_Mkt&HR
0	1	67.00	91.00	58.00	55.0	58.80	270000.0	1	1	1	1	0	0	1	0	1
1	2	79.33	78.33	77.48	86.5	66.28	200000.0	1	0	1	0	1	0	1	1	0
2	3	65.00	68.00	64.00	75.0	57.80	250000.0	1	0	0	0	0	0	0	0	0
3	4	56.00	52.00	52.00	66.0	59.43	265000.0	1	0	0	0	1	0	1	0	1
4	5	85.80	73.60	73.30	96.8	55.50	425000.0	1	0	0	1	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
210	211	80.60	82.00	77.60	91.0	74.49	400000.0	1	1	1	1	0	0	0	0	0
211	212	58.00	60.00	72.00	74.0	53.62	275000.0	1	1	1	0	1	0	1	0	0
212	213	67.00	67.00	73.00	59.0	69.72	295000.0	1	1	1	1	0	0	0	1	0
213	214	74.00	66.00	58.00	70.0	60.23	204000.0	0	1	1	1	0	0	0	0	1
214	215	62.00	58.00	53.00	89.0	60.22	265000.0	1	0	1	0	1	0	0	0	1

215 rows × 16 columns

numeric_features = ['ssc_p', 'hsc_p', 'mba_p', 'degree_p','etest_p','salary']
categorical_features = ['gender', 'ssc_b', 'hsc_b', 'hsc_s', 'degree_t', 'workex','specialisation']

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()  

X= scaler.fit_transform(X)

X

array([[-1.72401341, -0.02808697,  2.2688123 , ...,  1.62605898,
        -0.72444647,  1.12390297],
       [-1.70790113,  1.11336869,  1.10344799, ...,  1.62605898,
         1.38036423, -0.88975652],
       [-1.69178886, -0.21323793,  0.15331275, ..., -0.61498384,
        -0.72444647, -0.88975652],
       ...,
       [ 1.69178886, -0.02808697,  0.06133451, ..., -0.61498384,
         1.38036423, -0.88975652],
       [ 1.70790113,  0.61994138, -0.03064373, ..., -0.61498384,
        -0.72444647,  1.12390297],
       [ 1.72401341, -0.49096436, -0.76646966, ..., -0.61498384,
        -0.72444647,  1.12390297]])

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=1,stratify=y)

#Pipeline(steps=[('name_of_preprocessor', preprocessor),
#               ('name_of_ml_model', ml_model())])

X_train.shape

(172, 16)

X_test.shape

(43, 16)

y_train.shape

(172,)

y_test.shape

(43,)

#Preprocessor

X_train
X_test

array([[ 1.62733976e+00, -2.24989846e+00, -5.82513175e-01,
        -1.86632911e-01,  1.55223634e+00,  1.10281049e-01,
        -2.08630946e-01, -1.35238581e+00, -9.23822643e-01,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-4.35031420e-01,  1.57063988e-01, -3.98556692e-01,
         3.58206709e-01, -3.85091762e-01,  1.23395855e-02,
        -5.28936955e-01, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
         1.12390297e+00],
       [ 7.89501466e-01,  1.56421127e+00,  2.82082292e-01,
        -1.86632911e-01,  5.96407276e-01, -1.64235567e+00,
        -3.36753350e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00,  1.38036423e+00,
         1.12390297e+00],
       [ 1.17619606e+00, -2.13237928e-01,  4.75236599e-01,
        -4.86294703e-01, -1.14009102e+00, -9.75666407e-01,
        -2.08630946e-01,  7.39433966e-01, -9.23822643e-01,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [-1.64345203e+00, -1.13899272e+00, -1.52069123e+00,
         1.19839375e-01, -1.29109087e+00, -1.83823859e+00,
        -2.08630946e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00,  1.38036423e+00,
        -8.89756521e-01],
       [ 1.93347298e-01, -6.02054939e-01,  1.90104051e-01,
        -2.41116874e-01,  7.97237079e-01,  3.54275572e-01,
         8.43963129e+00,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [ 1.41788018e+00, -1.20662449e-01,  8.89138684e-01,
         7.66836425e-01,  8.98406980e-01, -5.71872653e-01,
        -8.05085429e-02,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
         1.12390297e+00],
       [ 1.61122748e-02, -5.83539843e-01,  1.44100813e+00,
         3.58206709e-01,  8.98406980e-01, -6.81842016e-01,
         2.39797466e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [-1.65956431e+00,  1.71233203e+00,  6.68390905e-01,
         9.43909302e-01,  1.86480603e+00, -1.16467625e+00,
         1.84132751e+00,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [-9.82848764e-01,  3.32031643e-01,  5.19386155e-01,
        -1.04906968e-01, -3.09591836e-01,  1.60689534e+00,
        -2.08630946e-01, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-1.17619606e+00, -4.90964364e-01, -1.41031735e+00,
        -1.95736168e+00, -2.76371869e-01,  8.45069797e-02,
        -2.08630946e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
         4.30644338e+00, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [ 1.04729786e+00,  5.27365904e-01, -7.66469657e-01,
        -1.41252206e+00,  8.98406980e-01, -1.65610184e+00,
         2.39797466e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-6.12266443e-01,  5.27365904e-01,  6.13203961e-01,
        -5.04230063e-02, -1.58591984e-01,  9.95190764e-01,
        -8.05085429e-02,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00,  1.38036423e+00,
        -8.89756521e-01],
       [-1.25675744e+00, -4.90964364e-01,  6.13345137e-02,
        -1.14010225e+00,  3.69907498e-01, -1.88806846e+00,
        -2.08630946e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [ 8.70062840e-01, -1.08344743e+00, -1.41031735e+00,
        -1.20820720e+00, -1.09252607e+00,  7.59156232e-02,
        -2.08630946e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [ 3.70582321e-01, -4.90964364e-01, -1.22621969e-01,
        -8.67682437e-01,  8.98406980e-01,  3.21628418e-01,
        -2.08630946e-01,  7.39433966e-01, -9.23822643e-01,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [ 1.48232928e+00,  1.57063988e-01, -1.22621969e-01,
        -1.27631215e+00,  6.79077939e-02, -1.11312811e+00,
        -2.08630946e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [ 6.12266443e-01,  2.04560376e+00, -6.19163295e-02,
         6.64678996e-01, -7.59213209e-03,  1.63547459e-01,
         1.52102150e+00,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
         1.12390297e+00],
       [-1.43399246e+00, -3.98388886e-01, -3.06437275e-02,
        -3.22842817e-01, -3.09591836e-01,  3.09600519e-01,
        -2.08630946e-01, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-1.11174696e+00,  5.27365904e-01, -7.66469657e-01,
        -5.04230063e-02, -1.38924078e+00, -9.30991353e-01,
        -5.28936955e-01, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [ 5.15592794e-01,  8.97667820e-01,  3.37269237e-01,
        -1.00389234e+00, -1.06459110e+00, -1.34853128e+00,
        -7.85181762e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [-1.19230834e+00,  1.82342261e+00, -1.22621969e-01,
         1.99272557e+00,  1.20040668e+00,  1.80449654e+00,
        -2.72692148e-01, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [-1.49844156e+00, -4.90964364e-01, -1.77823031e+00,
        -2.22978149e+00,  2.94407572e-01, -1.25746290e+00,
        -2.08630946e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-1.46621701e+00, -3.98388886e-01, -1.22480793e-02,
        -1.04906968e-01, -9.13591244e-01,  4.49867400e-02,
         2.39797466e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [-1.14397151e+00, -1.50929463e+00, -2.05416503e+00,
        -1.27631215e+00, -6.11591540e-01, -1.86057612e+00,
        -2.08630946e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [-1.09563469e+00,  1.26796974e+00,  1.53312755e-01,
        -3.22842817e-01,  1.57790631e+00,  4.84232826e-02,
         1.66195615e+00,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
        -8.89756521e-01],
       [ 9.66736489e-02,  6.16238364e-01,  1.16507341e+00,
         8.57868989e-02,  3.73285680e-03,  1.37773390e-01,
        -1.64473411e-02, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [ 2.90020947e-01,  1.54569617e+00,  6.13203961e-01,
         9.03046330e-01,  2.18907646e-01,  1.89900146e+00,
         8.80409484e-01, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [-9.98961039e-01,  8.05092341e-01, -2.14600210e-01,
         7.66836425e-01, -1.06459110e+00,  7.30576985e-01,
        -2.08630946e-01, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
         1.12390297e+00],
       [-1.72401341e+00, -2.80869697e-02,  2.26881230e+00,
        -1.14010225e+00, -1.29109087e+00, -5.97646723e-01,
        -1.44569745e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
         1.12390297e+00],
       [ 1.14397151e+00,  6.44885092e-02, -9.50426139e-01,
         2.21996804e-01,  6.79077939e-02,  9.95190764e-01,
         8.80409484e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
         1.12390297e+00],
       [ 3.54470046e-01,  8.69895176e-01,  2.14924059e+00,
        -5.04230063e-02,  1.35140654e+00,  1.07766779e+00,
        -4.00814552e-01,  7.39433966e-01, -9.23822643e-01,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [-9.18399665e-01,  7.31031958e-01,  6.31599609e-01,
         2.76480766e-01, -5.36091614e-01,  1.20590677e-01,
        -1.04142657e+00, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [ 1.57900293e+00, -5.83539843e-01, -3.98556692e-01,
        -1.86632911e-01, -7.62591392e-01, -9.39582710e-01,
        -4.00814552e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [ 1.45010473e+00,  1.54199315e+00, -1.22636086e+00,
         3.35482462e+00, -9.64931193e-01,  1.27698726e+00,
        -2.72692148e-01, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
         1.12390297e+00],
       [-2.09459573e-01, -8.61266280e-01, -3.98556692e-01,
        -3.22842817e-01, -1.37565079e+00, -1.25574463e+00,
        -2.72692148e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [-1.16008379e+00,  1.57063988e-01,  1.07309517e+00,
         7.66836425e-01, -8.30920581e-02,  7.93521658e-02,
         2.39797466e-01, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-1.67567658e+00, -1.04641724e+00, -1.31833910e+00,
        -1.95736168e+00, -4.60591688e-01, -4.89395632e-01,
        -2.08630946e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00, -7.24446475e-01,
         1.12390297e+00],
       [-3.86694596e-01,  1.54569617e+00,  1.16507341e+00,
         2.21996804e-01,  8.98406980e-01,  7.58069326e-01,
         2.39797466e-01,  7.39433966e-01,  1.08245885e+00,
         8.00762995e-01, -1.05254128e+00,  1.16732059e+00,
        -2.32210182e-01,  1.62605898e+00,  1.38036423e+00,
        -8.89756521e-01],
       [ 1.70790113e+00,  6.19941383e-01, -3.06437275e-02,
        -1.14010225e+00, -1.58591984e-01, -3.51933928e-01,
        -9.90177608e-01, -1.35238581e+00,  1.08245885e+00,
         8.00762995e-01,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
         1.12390297e+00],
       [-1.45010473e+00, -1.13899272e+00,  6.13345137e-02,
        -3.22842817e-01, -9.13591244e-01,  8.59447332e-01,
        -2.08630946e-01, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01, -7.24446475e-01,
        -8.89756521e-01],
       [-1.48232928e+00, -2.13237928e-01,  7.97160443e-01,
         3.58206709e-01, -7.59213209e-03,  4.09260254e-01,
        -1.04142657e+00, -1.35238581e+00, -9.23822643e-01,
        -1.24880896e+00,  9.50081506e-01, -8.56662692e-01,
        -2.32210182e-01, -6.14983844e-01,  1.38036423e+00,
        -8.89756521e-01],
       [ 2.73908672e-01, -2.80869697e-02,  4.29247478e-01,
        -2.77893548e-01, -6.11591540e-01, -1.74951985e-01,
        -4.00814552e-01,  7.39433966e-01, -9.23822643e-01,
        -1.24880896e+00, -1.05254128e+00,  1.16732059e+00,
         4.30644338e+00, -6.14983844e-01,  1.38036423e+00,
         1.12390297e+00]])

#https://medium.com/analytics-vidhya/evaluating-a-random-forest-model-9d165595ad56

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

# Instantiate and fit the RandomForestClassifier
forest = RandomForestClassifier()
forest.fit(X_train, y_train)

RandomForestClassifier()

# Make predictions for the test set
y_pred_test = forest.predict(X_test)

# View accuracy score
accuracy_score(y_test, y_pred_test)

0.9534883720930233

# View confusion matrix for test data and predictions
confusion_matrix(y_test, y_pred_test)

array([[11,  2],
       [ 0, 30]], dtype=int64)

# Get and reshape confusion matrix data
matrix = confusion_matrix(y_test, y_pred_test)
matrix = matrix.astype('float') / matrix.sum(axis=1)[:, np.newaxis]

# Build the plot
plt.figure(figsize=(16,7))
sns.set(font_scale=1.4)
sns.heatmap(matrix, annot=True, annot_kws={'size':10},
            cmap=plt.cm.Greens, linewidths=0.2)
# Add labels to the plot
class_names = ['placed','not_placed']
tick_marks = np.arange(len(class_names))
tick_marks2 = tick_marks + 0.5
plt.xticks(tick_marks, class_names, rotation=25)
plt.yticks(tick_marks2, class_names, rotation=0)
plt.xlabel('Predicted label')
plt.ylabel('True label')
plt.title('Confusion Matrix for Random Forest Model')
plt.show()

# View the classification report for test data and predictions
print(classification_report(y_test, y_pred_test))

              precision    recall  f1-score   support

           0       1.00      0.85      0.92        13
           1       0.94      1.00      0.97        30

    accuracy                           0.95        43
   macro avg       0.97      0.92      0.94        43
weighted avg       0.96      0.95      0.95        43

from sklearn.linear_model import LogisticRegression

#https://towardsdatascience.com/building-a-logistic-regression-in-python-step-by-step-becd4d56c9c8

import statsmodels.api as sm
logit_model=sm.Logit(y,X)
result=logit_model.fit()
print(result.summary2())

C:\Users\lance\anaconda3\lib\site-packages\statsmodels\compat\pandas.py:61: FutureWarning: pandas.Int64Index is deprecated and will be removed from pandas in a future version. Use pandas.Index with the appropriate dtype instead.
  from pandas import Int64Index as NumericIndex

Optimization terminated successfully.
         Current function value: 0.359486
         Iterations 7
                         Results: Logit
=================================================================
Model:              Logit            Pseudo R-squared: 0.421     
Dependent Variable: y                AIC:              186.5789  
Date:               2022-04-20 16:32 BIC:              240.5091  
No. Observations:   215              Log-Likelihood:   -77.289   
Df Model:           15               LL-Null:          -133.39   
Df Residuals:       199              LLR p-value:      6.1118e-17
Converged:          1.0000           Scale:            1.0000    
No. Iterations:     7.0000                                       
-------------------------------------------------------------------
           Coef.    Std.Err.      z      P>|z|     [0.025    0.975]
-------------------------------------------------------------------
x1         0.3047     0.2134    1.4283   0.1532   -0.1134    0.7229
x2         1.7088     0.3696    4.6233   0.0000    0.9844    2.4331
x3         1.0688     0.3421    3.1240   0.0018    0.3982    1.7393
x4         1.0069     0.3021    3.3327   0.0009    0.4147    1.5990
x5        -0.4167     0.2312   -1.8021   0.0715   -0.8699    0.0365
x6        -1.1309     0.2821   -4.0082   0.0001   -1.6838   -0.5779
x7         0.3161     0.2310    1.3687   0.1711   -0.1366    0.7688
x8         0.2620     0.2405    1.0892   0.2761   -0.2094    0.7334
x9         0.1692     0.3005    0.5632   0.5733   -0.4197    0.7582
x10       -0.0474     0.2853   -0.1662   0.8680   -0.6066    0.5118
x11       -0.8725     0.5104   -1.7093   0.0874   -1.8729    0.1279
x12       -0.5243     0.5506   -0.9521   0.3410   -1.6035    0.5550
x13       -0.3586     0.2565   -1.3981   0.1621   -0.8613    0.1441
x14       -0.5951     0.2973   -2.0017   0.0453   -1.1779   -0.0124
x15        0.5814     0.2317    2.5098   0.0121    0.1274    1.0355
x16       -0.1698     0.2211   -0.7679   0.4426   -0.6032    0.2636
=================================================================

#https://towardsdatascience.com/building-a-logistic-regression-in-python-step-by-step-becd4d56c9c8
from sklearn.linear_model import LogisticRegression
from sklearn import metrics
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
logreg = LogisticRegression()
logreg.fit(X_train, y_train)

LogisticRegression()

y_pred = logreg.predict(X_test)
print('Accuracy of logistic regression classifier on test set: {:.2f}'.format(logreg.score(X_test, y_test)))

Accuracy of logistic regression classifier on test set: 0.85

from sklearn.metrics import confusion_matrix
confusion_matrix = confusion_matrix(y_test, y_pred)
print(confusion_matrix)

[[12  7]
 [ 3 43]]

from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))

              precision    recall  f1-score   support

           0       0.80      0.63      0.71        19
           1       0.86      0.93      0.90        46

    accuracy                           0.85        65
   macro avg       0.83      0.78      0.80        65
weighted avg       0.84      0.85      0.84        65

from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve
logit_roc_auc = roc_auc_score(y_test, logreg.predict(X_test))
fpr, tpr, thresholds = roc_curve(y_test, logreg.predict_proba(X_test)[:,1])
plt.figure()
plt.plot(fpr, tpr, label='Logistic Regression (area = %0.2f)' % logit_roc_auc)
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
plt.savefig('Log_ROC')
plt.show()

XGBOOST

#https://towardsdatascience.com/beginners-guide-to-xgboost-for-classification-problems-50f75aac5390
# pip
!pip install xgboost

# conda
#conda install -c conda-forge xgboost

Requirement already satisfied: xgboost in c:\users\lance\anaconda3\lib\site-packages (1.6.0)
Requirement already satisfied: numpy in c:\users\lance\anaconda3\lib\site-packages (from xgboost) (1.21.5)
Requirement already satisfied: scipy in c:\users\lance\anaconda3\lib\site-packages (from xgboost) (1.7.3)

WARNING: Ignoring invalid distribution -illow (c:\users\lance\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\users\lance\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\users\lance\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\users\lance\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\users\lance\anaconda3\lib\site-packages)
WARNING: Ignoring invalid distribution -illow (c:\users\lance\anaconda3\lib\site-packages)
WARNING: You are using pip version 21.2.4; however, version 22.0.4 is available.
You should consider upgrading via the 'C:\Users\lance\anaconda3\python.exe -m pip install --upgrade pip' command.

X_train_xg, X_test_xg, y_train_xg, y_test_xg= train_test_split(X, y, test_size=0.3, random_state=0)
import xgboost as xgb

xgb_cl = xgb.XGBClassifier()

print(type(xgb_cl))

<class 'xgboost.sklearn.XGBClassifier'>

from sklearn.metrics import accuracy_score

# Init classifier
xgb_cl = xgb.XGBClassifier()

# Fit
xgb_cl.fit(X_train_xg, y_train_xg)

# Predict
preds_xg = xgb_cl.predict(X_test_xg)

# Score
accuracy_score(y_test_xg, preds_xg)

[17:01:18] WARNING: ..\src\learner.cc:1061: Starting in XGBoost 1.3.0, the default evaluation metric used with the objective 'binary:logistic' was changed from 'error' to 'logloss'. Explicitly set eval_metric if you'd like to restore the old behavior.

C:\Users\lance\anaconda3\lib\site-packages\xgboost\sklearn.py:888: UserWarning:

The use of label encoder in XGBClassifier is deprecated and will be removed in a future release. To remove this warning, do the following: 1) Pass option use_label_encoder=False when constructing XGBClassifier object; and 2) Encode your labels (y) as integers starting with 0, i.e. 0, 1, 2, ..., [num_class - 1].

0.9230769230769231

from sklearn.metrics import classification_report
print(classification_report(y_test_xg, preds_xg))

              precision    recall  f1-score   support

           0       0.82      0.95      0.88        19
           1       0.98      0.91      0.94        46

    accuracy                           0.92        65
   macro avg       0.90      0.93      0.91        65
weighted avg       0.93      0.92      0.92        65